© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177493
    Prev
    Next
    INDEX
    Explanations

    place names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mes
    0.45
    Mes
    0.41
     tor
    0.38
     Yah
    0.36
     Mesh
    0.36
    вов
    0.36
    雨
    0.35
     Nip
    0.35
    정과
    0.35
     tuck
    0.35
    POSITIVE LOGITS
    Shark
    0.42
    anjut
    0.40
     anten
    0.39
     اسٹ
    0.39
    ुआ
    0.39
     Chiang
    0.39
    ARTI
    0.39
    𝒇
    0.39
    鯊
    0.38
    goatee
    0.38
    Activations Density 0.000%

    No Known Activations